Upload 14 files

config.json

@@ -0,0 +1,78 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 2.0,
+  "max_length": 512,
+  "max_position_embeddings": 1024,
+  "min_length": 64,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 512,
+  "min_length": 64,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.26.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e2fe3eb711940153ef645f93a9f211ae601e0d8d53b358625de0ad14bf4427
+size 1115513717

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ddc4ac7a1b638274427fa912fcd63896f39301c3e8bad4def1b2481ae078b5
+size 557969145

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2866a56f734b09b00e139e6b47289fad99ea508d08f6baa40ba6046d9d3778c9
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e8e82df2a218f79477ba0b03e6a9ab23f1e5afc34023beded891ff592b6d44
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a7811ebb1ea4811719a146b86ebb37e3ab13fed96eb0b5894461332b6f070ec
+size 623

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "name_or_path": "facebook/bart-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,149 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "global_step": 39375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.902023616171372e-05,
+      "loss": 2.3606,
+      "step": 5625
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 108.1064,
+      "eval_loss": 2.050605297088623,
+      "eval_rouge1": 43.1144,
+      "eval_rouge2": 19.9792,
+      "eval_rougeL": 29.3193,
+      "eval_rougeLsum": 29.3219,
+      "eval_runtime": 6630.4724,
+      "eval_samples_per_second": 3.016,
+      "eval_steps_per_second": 3.016,
+      "step": 5625
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.914534041525834e-05,
+      "loss": 2.0883,
+      "step": 11250
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 111.923,
+      "eval_loss": 1.9714523553848267,
+      "eval_rouge1": 43.2087,
+      "eval_rouge2": 20.0241,
+      "eval_rougeL": 29.2716,
+      "eval_rougeLsum": 29.2729,
+      "eval_runtime": 6876.0309,
+      "eval_samples_per_second": 2.909,
+      "eval_steps_per_second": 2.909,
+      "step": 11250
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.9272200517975506e-05,
+      "loss": 1.9401,
+      "step": 16875
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 110.7088,
+      "eval_loss": 1.9192545413970947,
+      "eval_rouge1": 43.7675,
+      "eval_rouge2": 20.4219,
+      "eval_rougeL": 29.736,
+      "eval_rougeLsum": 29.736,
+      "eval_runtime": 6792.0963,
+      "eval_samples_per_second": 2.945,
+      "eval_steps_per_second": 2.945,
+      "step": 16875
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.9397304771520136e-05,
+      "loss": 1.8413,
+      "step": 22500
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 114.6206,
+      "eval_loss": 1.9106097221374512,
+      "eval_rouge1": 43.9857,
+      "eval_rouge2": 20.6259,
+      "eval_rougeL": 29.863,
+      "eval_rougeLsum": 29.8645,
+      "eval_runtime": 7084.2274,
+      "eval_samples_per_second": 2.823,
+      "eval_steps_per_second": 2.823,
+      "step": 22500
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.952240902506475e-05,
+      "loss": 1.7632,
+      "step": 28125
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 116.4429,
+      "eval_loss": 1.9056074619293213,
+      "eval_rouge1": 44.0791,
+      "eval_rouge2": 20.7132,
+      "eval_rougeL": 29.9243,
+      "eval_rougeLsum": 29.9263,
+      "eval_runtime": 7223.7263,
+      "eval_samples_per_second": 2.769,
+      "eval_steps_per_second": 2.769,
+      "step": 28125
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.9649269127781926e-05,
+      "loss": 1.6991,
+      "step": 33750
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 116.3214,
+      "eval_loss": 1.9034677743911743,
+      "eval_rouge1": 44.0398,
+      "eval_rouge2": 20.6289,
+      "eval_rougeL": 29.862,
+      "eval_rougeLsum": 29.8651,
+      "eval_runtime": 7200.6944,
+      "eval_samples_per_second": 2.778,
+      "eval_steps_per_second": 2.778,
+      "step": 33750
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 1.9777885079671656e-05,
+      "loss": 1.6457,
+      "step": 39375
+    },
+    {
+      "epoch": 7.0,
+      "eval_gen_len": 113.2878,
+      "eval_loss": 1.9000203609466553,
+      "eval_rouge1": 43.9966,
+      "eval_rouge2": 20.5908,
+      "eval_rougeL": 29.9303,
+      "eval_rougeLsum": 29.93,
+      "eval_runtime": 7006.6993,
+      "eval_samples_per_second": 2.854,
+      "eval_steps_per_second": 2.854,
+      "step": 39375
+    }
+  ],
+  "max_steps": 50625,
+  "num_train_epochs": 9,
+  "total_flos": 3.353631721258291e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a54bb8d38bc5218dace22ecff872d491cbca1351b884382522e9f20d455dc27
+size 3631